Gclaw is a Gcore-hosted, fully managed version of OpenClaw—a popular open-source AI agent framework with over 220,000 GitHub stars—with built-in inference powered by Gcore GPU infrastructure. Click Start to receive a fully functional OpenClaw instance with inference already connected. No VPS setup, no SSH, no separate inference provider, and no token management required.
A fully configured OpenClaw instance is ready in seconds—click Start and begin chatting within approximately one minute. Inference runs using the Kimi-K2.5 model on Gcore H200 GPUs, with no provider setup, API token management, or usage optimization required.
Each account receives a dedicated virtual machine with a personal OpenClaw instance. Data and configuration are fully separated from other accounts. The inference model runs on Gcore GPUs on-premise in the EU, and all chat history and personal data reside solely on the dedicated VM. Gcore does not store this data centrally.
The AI agent can connect to Telegram, Discord, and other messaging platforms through built-in integrations.
TipThe Gclaw assistant is interactive. Ask questions directly in the chat—the assistant provides step-by-step instructions, configuration commands, and troubleshooting help. If something is not covered in the documentation, ask the assistant.
InfoGclaw is currently in beta. During the beta period, each account is limited to one Gclaw instance, and service levels, guarantees, or support commitments do not apply.
Security model
Each Gclaw account receives an isolated, dedicated virtual machine. The OpenClaw agent running on this VM has full access to the VM environment, including the ability to execute commands and modify system configuration. This is by design—OpenClaw agents require system-level access to perform their intended functions.
Each account has a unique API key for LLM inference. API keys are not shared between accounts. The dedicated VM has no access to Gcore’s internal backend network or other customer environments.
WarningThe OpenClaw agent can execute any command on the dedicated VM, including opening SSH access or modifying system files. Treat the agent as having full administrative privileges on the instance.
Shared responsibility
Security is a shared responsibility between Gcore and the customer.
| Responsibility | Gcore | Customer |
|---|
| Physical infrastructure security | Yes | No |
| VM isolation between accounts | Yes | No |
| Network isolation from Gcore backend | Yes | No |
| Unique API key provisioning | Yes | No |
| Platform availability and updates | Yes | No |
| Safe usage of the agent | No | Yes |
| Protection of third-party API keys | No | Yes |
| Content and prompts sent to the agent | No | Yes |
| Actions performed by the agent on the VM | No | Yes |
| Compliance with applicable laws | No | Yes |
Security considerations
The OpenClaw agent executes commands based on prompts. The following security considerations apply:
-
Prompt safety: Prompts that could compromise the VM or expose sensitive data should be avoided. The agent follows instructions literally and does not apply additional security filtering.
-
Credential protection: API keys and tokens provided to the agent are stored in the VM configuration. Credentials should not grant access beyond what the agent requires.
-
Third-party integrations: When connecting Telegram, Discord, or other platforms, bot tokens must be secured. The permissions granted to connected platforms should be understood before integration.
-
Data sensitivity: Confidential business data, personal information, or regulated data should not be sent through the agent unless appropriate safeguards are in place.
-
Monitoring: Agent activity should be reviewed periodically. The agent logs actions in the workspace, and connected platforms (Telegram, Discord) retain conversation history.
For security hardening recommendations for OpenClaw installations, refer to the official OpenClaw security documentation.
Limits and quotas
The Kimi-K2.5 model has the following limits:
| Limit | Value |
|---|
| Context window | 200,000 tokens |
| Maximum output | 32,000 tokens |
| Reasoning | Enabled |
Available skills
Gclaw includes 53 built-in OpenClaw skills organized by category. Ask the assistant “List all available skills” for the complete list.
Key skills include:
| Category | Skills |
|---|
| Communication | discord, slack, voice-call, imsg |
| Productivity | notion, obsidian, trello, apple-notes, apple-reminders |
| Development | coding-agent, github, gh-issues |
| Media & AI | openai-image-gen, openai-whisper, spotify-player, gifgrep |
| Utilities | weather, summarize, config-backup, telegram-channel-setup |
| Hardware & IoT | openhue, sonoscli, wacli (WhatsApp) |
| Email & Web | himalaya (email), blogwatcher |
“Add my OpenAI key: sk-abc123…”
The assistant stores the key securely in the instance configuration.
Supported integrations include:
| Integration | Configuration |
|---|
| OpenAI (DALL-E, GPT, Whisper) | API key |
| Spotify | Client ID, Client Secret, Redirect URI |
| Brave Search | API key for web search |
| GitHub | Personal access token |
| Notion | Integration token |
Pricing
| Plan | Price | Includes |
|---|
| Start | 35 EUR/month (39 USD/month) | Dedicated OpenClaw instance + unlimited inference |
InfoDuring the beta period, Gclaw is available at no charge.
Third-party products
Gclaw includes OpenClaw (an open-source AI agent framework) and Kimi (a large language model for inference).
These are third-party products and should be considered Third Party Products under the Master Services Agreement. The Gclaw Terms and Conditions apply in addition to the MSA. Gcore assumes no liability for any technical errors, security vulnerabilities, incompatibilities, instabilities, or actions of such Third Party Products.
Support scope
Gcore provides support for infrastructure and billing issues. For OpenClaw-specific questions, refer to the official OpenClaw documentation.
| Issue type | Gcore support |
|---|
| Service down or 500 errors | Yes |
| Billing and subscription issues | Yes |
| OpenClaw usage questions | No - refer to OpenClaw docs |
| Feature requests | Logged for consideration |
